This paper proposes a validation framework that combines the flexibility of LLMs with the logic reasoning capabilities of Answer Set Programming as a complementary layer to existing guardrail mechanisms and demonstrates the practical implementation through a modular architecture that supports customizable validation components.
Abstract
Large language models (LLMs) have demonstrated significant capabilities in natural language understanding and decision support. However, their deployment in critical environments requires robust mechanisms to ensure dependability and prevent erroneous inputs or outputs from compromising system dependability. This paper presents a symbolic logic reasoning approach for enhancing the validation of both user inputs and LLM outputs in critical systems. We propose a validation framework that combines the flexibility of LLMs with the logic reasoning capabilities of Answer Set Programming (ASP) as a complementary layer to existing guardrail mechanisms. The approach enables systematic validation through declarative patterns for fault tolerance and logic reasoning. Our method validates user prompts and LLM responses against external knowledge bases and domain-specific constraints using multiple strategies, including redundancy-based validation, knowledge base auditing, and consistency checking. By transforming natural language interactions into logical representations, the framework leverages ASP’s non-monotonic reasoning to detect logical inconsistencies, contradictions, knowledge reproduction errors, and constraint violations throughout the interaction pipeline. The system provides both binary decision outputs (Go/NoGo) and detailed feedback about the reasoning artifacts for auditability and explainability. We demonstrate the practical implementation through a modular architecture that supports customizable validation components.
Large language models are increasingly used to reason about software vulnerabilities, but their outputs can silently violate domain knowledge, limiting their reliability in safety-critical settings such as medical devices. Prior work either treats that output as a prediction to be scored or constrains it to walks within a single knowledge graph; neither checks whether reasoning over a binary is consistent with an independent body of domain knowledge. We present EntailLLM, which validates each LLM-proposed analyst path by entailment: the path is a traversal of the binary's function call graph, the domain knowledge is represented in a separate graph, and verification aligns the two under temporal annotated logic. Across three CWE classes, four LLMs, three prompting strategies, and seven binaries varying in size from 405 to 12,696 function call-graph nodes, domain knowledge raises pooled entailment from 78% to 98%, with entailment decreasing in only 3% of the experiments. EntailLLM is deployed end-to-end on real medical-device binaries, reaching 98% pooled entailment without per-device tuning. Our system inherits the formal guarantees of generalized annotated logic, providing logical verification of LLM output that is both explainable and grounded in well-defined semantics.
Kaustuv Mukherji, J. Patil, C. Payne et al.· 0 citations
Large Language Models (LLMs) excel at natural language understanding and generation but remain unreliable for multi-step logical reasoning, especially in safety-critical or compliance-sensitive domains. Recent neuro-symbolic approaches address this gap by coupling neural models with external symbolic engines, yet most integrations are bespoke and lack a standardized interface for tool-augmented agents. This paper presents Euclid-MCP, an open-source MCP server that provides deterministic logical reasoning via SWI-Prolog. Euclid-MCP introduces Euclid-IR, an engine-agnostic intermediate representation for Horn-clause logic that is human-readable, easy for LLMs to generate, and straightforward to compile into Prolog or alternative backends. The server exposes a compact tool interface that supports a translate-run-inspect-repair loop, enabling LLM clients to delegate inference while retaining full access to proof traces and derivation logs. We evaluate Euclid-MCP on a realistic IT security and compliance use case. Results show that while LLMs alone are sufficient on small knowledge bases, they hallucinate systematically on larger problems, whereas Euclid-MCP delivers exact answers with lower latency and more compact outputs. We argue that semantic RAG is fundamentally unsuited for rule enforcement, and that Euclid-MCP can serve as a stable, shared reasoning substrate for both RAG-based assistants and agentic systems.
A unified supervision framework is introduced that embeds programmatically verifiable checkers into synthesized instruction-conflict instances, enabling alignment without oracle labels or reasoning traces, supporting both instruction-tuned and reasoning models.
Sian-Yao Huang, Li-Hsien Chang, Che-Yu Lin et al.· Neural Information Processin...· 4 citations
Automated Compliance Checking (ACC) systems are fundamentally static, unable to easily adapt to new regulations, project constraints, organizational, or practitioner-defined rules. This paper presents a framework integrating Knowledge Graphs (KGs) and Large Language Models (LLMs) to support a more extensible design review environment. In this framework, the KG acts as a structured repository for rules and executable logic, while the LLM serves as an intelligent interface. The central innovation is the human-in-the-loop feedback mechanism, where new logic generated by the LLM is validated, executed, and permanently stored in the KG, transforming it into an active, evolving validation engine. Following a Design Science Research (DSR) methodology, we implement and evaluate the framework as a prototype embedded as an Autodesk Revit add-in, demonstrating its ability to retrieve and execute existing rules from the KG, capture new requests during design, and maintain a verifiable, adaptive compliance checking system. Across a two-experiment evaluation, the system achieved 100% mapping accuracy for six existing rules, while generating new executable rules from natural language succeeded in 70% of 20 trials. Performance was strong on parameter-based checks (100%) but dropped on rules involving spatial reasoning (20–60%), where the LLM still struggles to produce reliable logic.
Maen Alnuzha, Tanya Bloch· Journal of Information Techn...· 1 citation
SIRNA significantly reduces the number of false positives and false negatives while offering explainability for its findings, and is generalizable to domains where business logic exists in both natural language documentation and programmatic implementation.
Joseph Tafese, Milad Hooshyar, Sam Bayless et al.· 0 citations
In fast-evolving software systems, effective 'natural language requirements parsing' and downstream change effect analysis capability across a multitude of codes represents low-hanging-fruit in this regard. We present a structured framework to deploy Large Language Models (LLMs) for automating two essential software engineering tasks, namely requirement interpretation and change impact analysis Utilizing the inherent understanding of semantics offered by transformer-based LLMs, the novel approach advances by converting vague and unstructured requirement documents into structured but machine-readable specifications to offer a direct traceability mapping from requirements to system components. Additionally, the framework leverages LLM-driven dependency analysis to predict and quantify how change effects percolate through connected modules which can minimize manual effort and human errors. This approach combines prompt engineering and retrieval-augmented generation (RAG) for domain-relevant accuracy plus fine-tuning techniques. On open-source and enterprise-grade software projects, experimental evaluations show that disambiguation accuracy, traceability precision, and change impact coverage of our approach are orders of magnitude better than state-of-the-art rule-based or static analysis tools. Notes: The results illustrate the application of LLMs at scale and demonstrate how these can alter software engineering workflows by removing bottlenecks (at a massive scale) at different stages of the software development lifecycle. In this research, we provide a generalizable pipeline that helps to bridge the gap from NLP advancements into practice for software lifecycle management.
Nithya Krishnan, Kumaran Ramanujam, Suresh Babu Narra et al.· 2026 International Conferenc...· 0 citations
